plan-ml-review
CommunityRigorous ML strategy reviews that scale.
Authortim-krausz
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Plan and perform ML architecture and deployment strategy reviews.
Core Features & Use Cases
- Structured Step 0 landscape and data inventory (data-modality map, dataset scale, label structure)
- Architecture critique and tradeoff analysis (backbone, task-head design, multi-modal fusion)
- Training strategy, diagnostics, and multi-stage planning (LR schedules, gradient norms, warmup, checkpoints)
- Evaluation protocol and failure analysis (per-class metrics, distribution shifts, robustness)
- Deployment considerations and governance (monitoring, retraining triggers, versioning)
Quick Start
Run the initial data-inventory and architecture scoping to kick off the plan.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: plan-ml-review Download link: https://github.com/tim-krausz/mlstack/archive/main.zip#plan-ml-review Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.